US2023084278A1PendingUtilityA1
System and method for hypergraph-based multi-agent battlefield situation awareness
Assignee: ELECTRONICS & TELECOMMUNICATIONS RES INSTPriority: Sep 3, 2021Filed: Feb 18, 2022Published: Mar 16, 2023
Est. expirySep 3, 2041(~15 yrs left)· nominal 20-yr term from priority
Inventors:Jaeuk Baek
G06F 17/16G06N 20/00G06N 5/04G06N 5/02G06N 5/043G06N 5/022G06N 7/01G06N 3/084
28
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
The present invention relates to a system and method for hypergraph-based multi-agent battlefield situation awareness. The system for hypergraph-based multi-agent battlefield situation awareness according to the present invention includes a knowledge graph generation unit configured to receive pieces of data collected by agents as an input and generate agent knowledge graphs including nodes, relations, and node embedding vectors for each agent, a knowledge graph concatenation unit configured to analyze a similarity between the respective agents and a similarity between the pieces of data and concatenate the plurality of agent knowledge graphs to generate a global knowledge graph, and a battlefield situation awareness unit configured to infer a battlefield situation using a battlefield situation hierarchical structure and the global knowledge graph.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A system for hypergraph-based multi-agent battlefield situation awareness, comprising:
a knowledge graph generation unit configured to receive pieces of data collected by agents as an input and generate agent knowledge graphs including nodes, relations, and node embedding vectors for each agent; a knowledge graph concatenation unit configured to analyze a similarity between the respective agents and a similarity between pieces of data and concatenate the plurality of agent knowledge graphs to generate a global knowledge graph; and a battlefield situation awareness unit configured to infer a battlefield situation using a battlefield situation hierarchical structure and the global knowledge graph.
2 . The system of claim 1 , wherein the knowledge graph generation unit defines an object, which is recognized from the data collected by the agent, as the node to generate a node list, defines features of the respective nodes as a property to generate a property list, and defines a predetermined relation between the nodes as the relation to generate a relation list.
3 . The system of claim 1 , wherein the knowledge graph generation unit generates the node embedding vector by concatenating an embedding vector (vec1) related to the property of the node, an embedding vector (vec2) in which a node name is defined, and an embedding vector (vec3) related to the relation between the nodes,
trains the embedding vector (vec1) so that the embedding vector (vec1) is similar to a property vector directly related to each of the nodes and dissimilar to a property vector not related to each of the nodes, and trains the embedding vector (vec3) so that embedding vectors (vec3) of the nodes having the relation to each other become similar.
4 . The system of claim 1 , wherein the knowledge graph concatenation unit constructs an incidence matrix in a way to select an agent adjacent to a node of a specific agent knowledge graph, and
the adjacent agent includes a node having a node embedding vector similar to the node embedding vector of the node as a component of the agent knowledge graph.
5 . The system of claim 1 , wherein the knowledge graph concatenation unit includes:
a hypergraph-based random sample module configured to generate a hypergraph including hypernodes corresponding to each of the agents and hyperedges representing a set of adjacent agents of each of the nodes, and generate an agent list based on the hypergraph; an agent embedding learning module configured to derive an (agent, adjacent agent) pair by applying a context window to the agent list, and train the agent embedding vector so that a value of a cost function calculated from the (agent, adjacent agent) pair is minimized; and a similarity inference and concatenation module configured to generate the global knowledge graph by concatenating each agent knowledge graph through the analysis of the similarity between the agents using the agent embedding vector and an analysis of a similarity between data of a specific agent and data collected by an agent adjacent to the specific agent using the agent embedding vector.
6 . The system of claim 5 , wherein the hypergraph-based random sample module generates a hyperedge including a plurality of agents based on a similarity between the node embedding vectors assigned to each node of the agent knowledge graph and a node embedding vector of another agent knowledge graph, and generates a hypergraph including the hyperedge and a hypernode corresponding to an agent included in the hyperedge.
7 . The system of claim 5 , wherein the hypergraph-based random sample module generates the agent list in a way to move an arbitrary agent according to a random walk rule based on the hypergraph, and
the random walk rule defines a movement probability from a current agent to a next agent and includes a rule for determining the movement probability according to the number of hyperedges included in the hypergraph shared by an agent adjacent to the current agent and a previously visited agent.
8 . The system of claim 5 , wherein the cost function is defined for the (agent, adjacent agent) pair (i,j) according to the following Equation:
Cost
(
e
❘
e
j
,
ψ
f
)
=
-
(
log
σ
(
f
k
(
e
i
)
·
f
i
(
e
j
)
-
c
k
l
)
+
∑
m
∈
Ψ
f
∑
v
∈
Ψ
a
log
σ
(
-
f
m
(
e
v
)
·
f
l
(
e
j
)
+
c
ml
)
)
,
[
Equation
]
(here, in the above Equation, i, j, and v denote the agents,
k, l, and m denote nodes constructing the agent knowledge graph,
e i , e j , and e v denote the agent embedding vectors,
u k , u l , and u m denote the fixed vectors (relation aware vector) assigned to the node,
c denotes a dot product of the relation aware vectors of each of the nodes written in a subscript,
Ψ a denotes a set of agents, and Ψ f denotes a set of nodes constructing the agent knowledge graph,
σ denotes a sigmoid function, and
f denotes a vector function that returns a sum of the relation aware vector of the node written in the subscript and the agent embedding vector as an argument).
9 . The system of claim 8 , wherein the relation aware vector for an arbitrary knowledge graph node k is defined as u k =[U k,1 , U k,2 , . . . , U k,2n-1 , u k,2n , . . . , U k,d vec ] T , and
an arbitrary factor of u k is defined as
u
k
,
2
n
-
1
=
cos
(
(
k
❘
"\[LeftBracketingBar]"
Ψ
f
❘
"\[RightBracketingBar]"
)
2
n
-
1
d
vec
)
,
u
k
,
2
n
=
sin
(
(
k
❘
"\[LeftBracketingBar]"
Ψ
f
❘
"\[RightBracketingBar]"
)
2
n
-
1
d
vec
)
,
for
n
=
1
,
2
,
…
,
(here, in the above Equation, d vec denotes a dimension of u k ).
10 . The system of claim 8 , wherein the relation aware vector for an arbitrary knowledge graph node k is
u k u l =0 for k≠l with ∥ u k ∥=∥u i ∥=1, k,lεΨ f .
11 . The system of claim 1 , wherein the battlefield situation awareness unit defines the battlefield situation as a hierarchical structure composed of a higher concept and a lower concept,
trains a classification network using the knowledge graph possessed by the agent as an input value and the lower concept of the battlefield situation as a label, maps the global knowledge graph to the lower concept of the battlefield situation through the classification network, and infers the higher concept from the lower concept in the battlefield situation hierarchical structure to recognize the battlefield situation.
12 . A method of generating a knowledge graph, comprising:
collecting, by an agent, pieces of data; defining objects recognized from the data as nodes, defining a feature of the node as a property, and defining a predetermined relation between the nodes as a relation; training an embedding vector (vec1) related to the property of the node, training an embedding vector (vec3) related to the relation between the nodes, and then generating a node embedding vector by concatenating an embedding vector (vec2) in which a node name is defined with the vec1 and vec3; and generating an agent knowledge graph including the nodes, the relation, and the node embedding vectors.
13 . The method of claim 12 , wherein the embedding vector (vec1) related to the property of the node is trained to be similar to a property vector directly related to the node and dissimilar to a property vector not related to the node.
14 . The method of claim 12 , wherein the embedding vector (vec3) is trained in such a way that embedding vectors (vec3) of nodes having a relation to each other become similar.
15 . A method of concatenating a knowledge graph, comprising:
generating a hypergraph including hypernodes (agents) and a hyperedge based on an agent knowledge graph including nodes, relations, and node embedding vectors; constructing a training data set for generating an agent list by sampling an agent that is the hypernode on the hypergraph; training an agent embedding vector to minimize a cost function using, as training data, an (agent, adjacent agent) pair derived by applying a context window to the agent list; inferring a similarity between the agents using the agent embedding vector; inferring a similarity between the nodes of the agent knowledge graph using the agent embedding vector and a fixed vector (relation aware vector) assigned to each of the nodes of the agent knowledge graph; and generating a global knowledge graph by concatenating the knowledge graph based on the similarity between the agents and the similarity between the nodes (data similarity).
16 . The method of claim 15 , wherein each of the hypernodes corresponds to one of the agents,
the hyperedge includes a set of agents adjacent to each of the nodes, and the adjacent agent is determined according to a similarity between a node embedding vector of the node and a node embedding vector of a node included in the knowledge graph of the adjacent agent.
17 . The method of claim 15 , wherein the agent list is generated in a way to move an arbitrary agent according to a random walk rule based on the hypergraph, and
the random walk rule defines a movement probability from a current agent to a next agent, and includes a rule for determining the movement probability according to the number of hyperedges included in the hypergraph shared by an agent adjacent to the current agent and a previously visited agent.
18 . The method of claim 15 , wherein the cost function is defined for the (agent, adjacent agent) pair (i,j) according to the following equation:
Cost
(
e
❘
e
j
,
ψ
f
)
=
-
(
log
σ
(
f
k
(
e
i
)
·
f
i
(
e
j
)
-
c
k
l
)
+
∑
m
∈
Ψ
f
∑
v
∈
Ψ
a
log
σ
(
-
f
m
(
e
v
)
·
f
l
(
e
j
)
+
c
ml
)
)
,
[
Equation
]
(here, in the above Equation, i, j, and v denote the agents,
k, 1 , and m denote nodes constructing the agent knowledge graph,
e i , e j , and e v denote the agent embedding vectors,
u k , u l , and u m denote the fixed vectors (relation aware vector) assigned to the node,
c denotes a dot product of the relation aware vectors of each of the nodes written in a subscript,
Ψ a denotes a set of agents, and Ψ f denotes a set of nodes constructing the agent knowledge graph,
σ denotes a sigmoid function, and
f denotes a vector function that returns a sum of the relation aware vector of the node written in the subscript and the agent embedding vector as an argument).Join the waitlist — get patent alerts
Track US2023084278A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.